1 files changed, 34 insertions, 17 deletions

diff --git a/drivers/gpu/drm/xe/xe_lrc.c b/drivers/gpu/drm/xe/xe_lrc.c
index 63d74e27f54c..6e7b70532d11 100644
--- a/drivers/gpu/drm/xe/xe_lrc.c
+++ b/drivers/gpu/drm/xe/xe_lrc.c
@@ -40,6 +40,7 @@
 
 #define LRC_PPHWSP_SIZE				SZ_4K
 #define LRC_INDIRECT_RING_STATE_SIZE		SZ_4K
+#define LRC_WA_BB_SIZE				SZ_4K
 
 static struct xe_device *
 lrc_to_xe(struct xe_lrc *lrc)
@@ -910,7 +911,11 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
 {
 	xe_hw_fence_ctx_finish(&lrc->fence_ctx);
 	xe_bo_unpin_map_no_vm(lrc->bo);
-	xe_bo_unpin_map_no_vm(lrc->bb_per_ctx_bo);
+}
+
+static size_t wa_bb_offset(struct xe_lrc *lrc)
+{
+	return lrc->bo->size - LRC_WA_BB_SIZE;
 }
 
 /*
@@ -941,11 +946,19 @@ static void xe_lrc_finish(struct xe_lrc *lrc)
  * store it in the PPHSWP.
  */
 #define CONTEXT_ACTIVE 1ULL
-static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
+static int xe_lrc_setup_utilization(struct xe_lrc *lrc)
 {
-	u32 *cmd;
+	const size_t max_size = LRC_WA_BB_SIZE;
+	u32 *cmd, *buf = NULL;
 
-	cmd = lrc->bb_per_ctx_bo->vmap.vaddr;
+	if (lrc->bo->vmap.is_iomem) {
+		buf = kmalloc(max_size, GFP_KERNEL);
+		if (!buf)
+			return -ENOMEM;
+		cmd = buf;
+	} else {
+		cmd = lrc->bo->vmap.vaddr + wa_bb_offset(lrc);
+	}
 
 	*cmd++ = MI_STORE_REGISTER_MEM | MI_SRM_USE_GGTT | MI_SRM_ADD_CS_OFFSET;
 	*cmd++ = ENGINE_ID(0).addr;
@@ -966,9 +979,17 @@ static void xe_lrc_setup_utilization(struct xe_lrc *lrc)
 
 	*cmd++ = MI_BATCH_BUFFER_END;
 
-	xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR,
-			     xe_bo_ggtt_addr(lrc->bb_per_ctx_bo) | 1);
+	if (buf) {
+		xe_map_memcpy_to(gt_to_xe(lrc->gt), &lrc->bo->vmap,
+				 wa_bb_offset(lrc), buf,
+				 (cmd - buf) * sizeof(*cmd));
+		kfree(buf);
+	}
+
+	xe_lrc_write_ctx_reg(lrc, CTX_BB_PER_CTX_PTR, xe_bo_ggtt_addr(lrc->bo) +
+			     wa_bb_offset(lrc) + 1);
 
+	return 0;
 }
 
 #define PVC_CTX_ASID		(0x2e + 1)
@@ -1004,20 +1025,13 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	 * FIXME: Perma-pinning LRC as we don't yet support moving GGTT address
 	 * via VM bind calls.
 	 */
-	lrc->bo = xe_bo_create_pin_map(xe, tile, NULL, lrc_size,
+	lrc->bo = xe_bo_create_pin_map(xe, tile, NULL,
+				       lrc_size + LRC_WA_BB_SIZE,
 				       ttm_bo_type_kernel,
 				       bo_flags);
 	if (IS_ERR(lrc->bo))
 		return PTR_ERR(lrc->bo);
 
-	lrc->bb_per_ctx_bo = xe_bo_create_pin_map(xe, tile, NULL, SZ_4K,
-						  ttm_bo_type_kernel,
-						  bo_flags);
-	if (IS_ERR(lrc->bb_per_ctx_bo)) {
-		err = PTR_ERR(lrc->bb_per_ctx_bo);
-		goto err_lrc_finish;
-	}
-
 	lrc->size = lrc_size;
 	lrc->ring.size = ring_size;
 	lrc->ring.tail = 0;
@@ -1125,7 +1139,9 @@ static int xe_lrc_init(struct xe_lrc *lrc, struct xe_hw_engine *hwe,
 	map = __xe_lrc_start_seqno_map(lrc);
 	xe_map_write32(lrc_to_xe(lrc), &map, lrc->fence_ctx.next_seqno - 1);
 
-	xe_lrc_setup_utilization(lrc);
+	err = xe_lrc_setup_utilization(lrc);
+	if (err)
+		goto err_lrc_finish;
 
 	return 0;
 
@@ -1803,7 +1819,8 @@ struct xe_lrc_snapshot *xe_lrc_snapshot_capture(struct xe_lrc *lrc)
 	snapshot->seqno = xe_lrc_seqno(lrc);
 	snapshot->lrc_bo = xe_bo_get(lrc->bo);
 	snapshot->lrc_offset = xe_lrc_pphwsp_offset(lrc);
-	snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset;
+	snapshot->lrc_size = lrc->bo->size - snapshot->lrc_offset -
+		LRC_WA_BB_SIZE;
 	snapshot->lrc_snapshot = NULL;
 	snapshot->ctx_timestamp = lower_32_bits(xe_lrc_ctx_timestamp(lrc));
 	snapshot->ctx_job_timestamp = xe_lrc_ctx_job_timestamp(lrc);